In this paper, we propose a new zero order optimization method called minibatch stochastic three points (MiSTP) method to solve an unconstrained minimization problem in a setting where only an approximation of the objective function evaluation is possible. It is based on the recently proposed stochastic three points (STP) method (Bergou et al., 2020). At each iteration, MiSTP generates a random search direction in a similar manner to STP, but chooses the next iterate based solely on the approximation of the objective function rather than its exact evaluations. We also analyze our method's complexity in the nonconvex and convex cases and evaluate its performance on multiple machine learning tasks.

翻译：在本文中,我们提出了一种新的零顺序优化方法,称为微型批次随机三点(MISTP),在只可能接近客观功能评估的情况下解决一个不受限制的最小化问题,其依据是最近提议的随机三点(STP)方法(Bergou等人,2020年)。在每次迭代中,MISTP以与STP相似的方式产生随机搜索方向,但仅根据目标功能近似而非精确评估选择下一个迭代。我们还分析了我们的方法在非convex和convex案例中的复杂性,并评估了其在多机学习任务上的绩效。